© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 1496
    Prev
    Next
    INDEX
    Explanations

    the word stem "rib" for various terms related to human anatomy, biology, and politics

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "rib."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Coastal
    -0.75
     TAM
    -0.74
     Shannon
    -0.73
     Sunny
    -0.72
     Challenger
    -0.69
    TPS
    -0.67
     Gunn
    -0.66
     Lauder
    -0.66
     Irma
    -0.64
     Leone
    -0.64
    POSITIVE LOGITS
    bage
    1.18
    rib
    1.10
    ilib
    1.02
    unal
    1.00
    bon
    1.00
    leness
    0.99
    yrinth
    0.98
    ril
    0.97
    bled
    0.94
    bler
    0.92
    Activations Density 0.005%

    No Known Activations